CN110751639A - Intelligent assessment and damage assessment system and method for rice lodging based on deep learning - Google Patents
Intelligent assessment and damage assessment system and method for rice lodging based on deep learning Download PDFInfo
- Publication number
- CN110751639A CN110751639A CN201910983753.1A CN201910983753A CN110751639A CN 110751639 A CN110751639 A CN 110751639A CN 201910983753 A CN201910983753 A CN 201910983753A CN 110751639 A CN110751639 A CN 110751639A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- disaster
- lodging
- assessment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 235000007164 Oryza sativa Nutrition 0.000 title claims abstract description 42
- 235000009566 rice Nutrition 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000013135 deep learning Methods 0.000 title claims abstract description 21
- 240000007594 Oryza sativa Species 0.000 title 1
- 241000209094 Oryza Species 0.000 claims abstract description 41
- 238000005520 cutting process Methods 0.000 claims abstract description 18
- 238000012790 confirmation Methods 0.000 claims abstract description 10
- 238000011156 evaluation Methods 0.000 claims abstract description 3
- 238000013500 data storage Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
Abstract
The invention provides a rice lodging intelligent assessment and damage assessment system based on deep learning and an assessment and damage assessment method thereof, belongs to the field of rice lodging and damage assessment, and provides the rice lodging intelligent assessment and damage assessment system based on deep learning and an assessment and damage assessment method thereof, wherein the system can be matched with farmer information, can perform quantitative damage assessment, and is high in practical operability and automation degree. In the invention, the fast splicing software is used for fast splicing the images of the unmanned aerial vehicle; the image data loading module is used for loading the spliced complete unmanned aerial vehicle image, the polygon drawing module is used for drawing an right plot on the spliced image according to the information of farmers, the cutting module is used for cutting according to the drawn polygon, the disaster identification module is used for segmenting a disaster area according to a deep learning algorithm, and the disaster statistical module is used for counting the disaster proportion; and the confirmation list output module is used for outputting a disaster evaluation damage assessment report. The method is mainly used for evaluating and determining the damage of rice lodging.
Description
Technical Field
The invention belongs to the field of rice lodging assessment and damage, and particularly relates to a rice lodging intelligent assessment and damage assessment system based on deep learning and an assessment and damage assessment method thereof.
Background
Crop lodging is a main cause of yield reduction and crop quality reduction in agricultural production, and currently, few researches are made on crop lodging and damage assessment. Patent document No. CN108169138A describes a remote sensing damage assessment method for lodging disasters based on an unmanned aerial vehicle, which uses a thermal infrared image, and utilizes color characteristics, texture characteristics, and temperature characteristics to construct a discrimination model of a lodging region, and identifies the lodging region and a non-lodging region. The method adopts the thermal infrared image, so that the flying height of the unmanned aerial vehicle during data acquisition is required to be not too high, the requirement on the image of the flying is high, great inconvenience is brought to field operation, only one identification method is provided in the literature, a whole set of system with a whole flow is not formed, interference factors are excessive, the application scene of the method is greatly limited, the analysis process of the method is very complex, controlled factors are excessive, actual operation is difficult, and a lot of obstacles are brought to loss assessment.
Therefore, a rice lodging intelligent assessment damage assessment system and a rice lodging assessment damage assessment method based on deep learning, which can match with farmer information, can quantify damage assessment, have strong real operability and high automation degree, are needed.
Disclosure of Invention
Aiming at the defects that the existing damage assessment method cannot automatically match farmer information, cannot quantitatively assess damage, is poor in real operability and low in automation degree, the invention provides the intelligent rice lodging assessment damage assessment system which can match farmer information, is quantitative in damage assessment, is strong in real operability and high in automation degree and is based on deep learning, and the assessment damage assessment method thereof.
The invention relates to a rice lodging intelligent assessment damage assessment system based on deep learning and an assessment damage assessment method thereof, wherein the technical scheme comprises the following steps:
the invention relates to a rice lodging intelligent assessment damage assessment system based on deep learning, which comprises an image fast splicing module, an image editing module, a disaster situation processing module and a confirmation list output module, wherein the image fast splicing module comprises fast splicing software, and the fast splicing software is used for fast splicing unmanned aerial vehicle images to form a complete lodging image; the image editing function module comprises an image data loading module, a polygon drawing module, an edge clearing module, a cutting module and an image data storage module, wherein the image data loading module is used for loading a spliced complete lodging image, the polygon drawing module is used for drawing an entitlement land parcel boundary on the spliced lodging image according to farmer information, the edge clearing module is used for clearing images outside the drawn entitlement land parcel boundary, the cutting module is used for cutting the edge-cleared lodging image according to a preset farmer land parcel standard, and the image data storage module is used for storing the cut lodging image; the disaster situation processing module comprises a disaster situation recognition module and a disaster situation statistics module, wherein the disaster situation recognition module is used for recognizing the images of the cut right plot areas and recognizing rice lodging areas in the right plot areas; the disaster situation statistical module is used for comparing the disaster-affected image identified by the disaster situation with the original image and counting the disaster-affected proportion; and the confirmation list output module is used for matching the peasant household information with the disaster-suffered image and further outputting a disaster-suffered assessment damage assessment report.
Further: the quick-splicing software is specifically software Pix4 DMapper.
An assessment damage assessment method based on the intelligent rice lodging assessment damage assessment system based on deep learning comprises the following steps:
step one, acquiring an unmanned aerial vehicle image;
step two, the fast splicing software carries out fast splicing on the unmanned aerial vehicle remote sensing sequence images with the overlapping degree to form complete lodging images containing information of all land parcels of the peasant household;
step three, the image data loading module loads the spliced complete lodging image, the polygon drawing module is used for drawing an edge according to the complete lodging image, the edge clearing module clears a line that the drawn edge is not matched with the complete lodging image, the cutting module cuts the lodging image with the edge cleared according to a preset farmer land parcel standard, and the image data storage module stores the cut lodging image;
step four, the disaster recognition module recognizes the image of the right plot area obtained after cutting, and recognizes the rice lodging area in the right plot area;
step five, the disaster situation statistical module matches the screened disaster-suffered images with farmers, compares the disaster-suffered images with the lodging images and counts the disaster-suffered proportion;
and sixthly, the confirmation list output module is used for matching the peasant household information with the disaster-suffered image, and further outputting a disaster-suffered assessment damage assessment report.
Further: in the fourth step, the clipped lodging images are transmitted to a disaster identification module, the disaster identification module divides the lodging images into sub-blocks with fixed sizes according to the sizes of the input images, each sub-block is respectively input into a convolutional neural network model to identify and predict rice lodging areas, a first pixel area in a specified prediction result represents the lodging area, and a second pixel area in the specified prediction result represents other areas.
Further: and step five, automatically removing the black edge remained in the image according to the pixel value of the edge area of the disaster-suffered image, and then counting the proportion of the disaster-suffered area.
Further: in the sixth step, the disaster assessment damage assessment report includes farmer information, a disaster area and a disaster image.
The intelligent rice lodging assessment and damage assessment system and method based on deep learning have the beneficial effects that:
the intelligent rice lodging assessment and damage assessment system based on deep learning and the assessment and damage assessment method thereof have the advantages of convenience in operation, complete system, simple and clear structure, no overhigh requirement on aerial images of unmanned aerial vehicles, clear requirement, capability of combining lodging conditions with farmer information, capability of directly qualitatively and quantitatively analyzing disaster conditions without further analysis of generated disaster assessment and damage assessment reports, strong operability, difficulty in interference of operators and no influence on analysis results due to the fact that the height of the unmanned aerial vehicles cannot meet the requirement.
Drawings
FIG. 1 is a functional module schematic diagram of an intelligent assessment damage assessment system for rice lodging based on deep learning;
FIG. 2 is a flow chart of the operation of the damage assessment method for rice lodging in FIG. 1.
Detailed Description
The technical solutions of the present invention are further described below with reference to the following examples, but the present invention is not limited thereto, and any modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Example 1
The embodiment is described with reference to fig. 1 and fig. 2, in this embodiment, a rice lodging intelligent assessment damage assessment system based on deep learning according to this embodiment includes an image fast-splicing module, an image editing module, a disaster processing module, and a confirmation order output module, where the image fast-splicing module is configured to implement fast splicing of images of an unmanned aerial vehicle by calling fast-splicing software; the image fast splicing module comprises fast splicing software, and the fast splicing software is used for fast splicing the unmanned aerial vehicle images to form a complete lodging image; the image editing function module comprises an image data loading module, a polygon drawing module, an edge clearing module, a cutting module and an image data storage module, and can realize the accurate division of farmer land parcels; the image data loading module is used for loading the spliced complete lodging images, the polygon drawing module is used for drawing the boundary of the right parcel on the spliced lodging images according to the information of the peasant household, the edge clearing module is used for clearing images outside the boundary of the drawn right parcel, the cutting module is used for cutting the lodging images with edges cleared according to the preset standard of the peasant household parcel, and the image data storage module is used for storing the cut lodging images; the disaster situation processing module comprises a disaster situation recognition module and a disaster situation statistics module, wherein the disaster situation recognition module is used for recognizing the images of the right plot area obtained after cutting, screening the images suffering from the disaster according to a preset disaster situation threshold value and recognizing the rice lodging area in the right plot area; the disaster situation statistical module is used for comparing the disaster-affected image identified by the disaster situation with the original image and counting the disaster-affected proportion; and the confirmation list output module is used for matching the peasant household information with the disaster-suffered image and further outputting a disaster-suffered assessment damage assessment report. The quick-splicing software is specifically software Pix4 DMapper.
Example 2
The present embodiment is described with reference to embodiment 1, and in this embodiment, the method for evaluating damage of rice lodging intelligent evaluation damage system based on deep learning according to the present embodiment includes the following steps:
step one, acquiring an unmanned aerial vehicle image;
step two, the fast splicing software carries out fast splicing on the unmanned aerial vehicle remote sensing sequence images with the overlapping degree, the unmanned aerial vehicle image fast splicing software is called, the unmanned aerial vehicle remote sensing sequence images with a certain overlapping degree are obtained after the unmanned aerial vehicle flies, and fast splicing is carried out according to the overlapping area of the sequence images to obtain a whole image containing all plots of farmers;
step three, the image data loading module loads the spliced complete lodging image, the polygon drawing module is used for drawing an edge according to the complete lodging image, the edge clearing module clears a line that the drawn edge is not matched with the complete lodging image, the cutting module cuts the lodging image with the edge cleared according to a preset farmer land parcel standard, and the image data storage module stores the cut lodging image;
step four, the disaster recognition module recognizes the image of the right plot area obtained after cutting, and recognizes the rice lodging area in the right plot area; the clipped lodging images are transmitted to a disaster identification module, the disaster identification module automatically identifies the rice lodging disaster area, blocks are divided into sub-blocks with fixed sizes according to the size of the input images, each sub-block is respectively input into a convolutional neural network model to identify and predict the rice lodging area, a first pixel area in a specified prediction result represents the lodging area, and a second pixel area is specified to represent other areas; generating a rice disaster map; transmitting the image of the farmer's right land parcel saved in the last step to a disaster situation recognition module, partitioning the image into sub-blocks with fixed sizes by a functional module according to the size of the image, respectively transmitting each sub-block into a convolutional neural network model to recognize and predict a rice lodging area, wherein a red area of a predicted result pixel (255,0,0) represents the lodging area, and a black area of the pixel (0,0,0) represents other areas; after all the subblocks are predicted, a superposition strategy is adopted to avoid generating gaps in the subblock splicing process;
step five, the disaster situation statistical module matches the screened disaster-suffered images with farmers, compares the disaster-suffered images with the lodging images and counts the disaster-suffered proportion; automatically removing the black edge remained in the image according to the pixel value of the edge area of the disaster-suffered image and then counting the proportion of the disaster-suffered area; automatically counting the proportion of the rice disaster area according to the rice disaster map obtained in the step four; according to the image of the farmer rights land parcel and the rice disaster-suffered image intercepted in the third step and the fourth step, because the intercepted image may have an irregular shape, the image is stored in a polygonal external rectangle, and redundant black edges exist at the edge; during statistics, according to the pixel value of the image edge area, automatically removing the residual black edge in the image, and counting the proportion of the area affected by the disaster;
step six, the confirmation list output module is matched with the disaster-suffered image according to the information of the peasant household, and then a disaster-suffered assessment damage assessment report is output; automatically outputting a rice disaster situation report according to the rice disaster proportion determined in the step five; and automatically generating a statistical report containing the information of farmers, the disaster area and the disaster image according to the disaster image, the disaster statistical file and other information input by the user.
Claims (6)
1. A rice lodging intelligent assessment damage assessment system based on deep learning is characterized by comprising an image fast splicing module, an image editing module, a disaster situation processing module and a confirmation list output module, wherein the image fast splicing module comprises fast splicing software which is used for fast splicing unmanned aerial vehicle images to form a complete lodging image; the image editing function module comprises an image data loading module, a polygon drawing module, an edge clearing module, a cutting module and an image data storage module, wherein the image data loading module is used for loading a spliced complete lodging image, the polygon drawing module is used for drawing an entitlement land parcel boundary on the spliced lodging image according to farmer information, the edge clearing module is used for clearing images outside the drawn entitlement land parcel boundary, the cutting module is used for cutting the edge-cleared lodging image according to a preset farmer land parcel standard, and the image data storage module is used for storing the cut lodging image; the disaster situation processing module comprises a disaster situation recognition module and a disaster situation statistics module, wherein the disaster situation recognition module is used for recognizing the images of the cut right plot areas and recognizing rice lodging areas in the right plot areas; the disaster situation statistical module is used for comparing the disaster-affected image identified by the disaster situation with the original image and counting the disaster-affected proportion; and the confirmation list output module is used for matching the peasant household information with the disaster-suffered image and further outputting a disaster-suffered assessment damage assessment report.
2. The intelligent assessment damage assessment system for rice lodging based on deep learning of claim 1, wherein the fast-splicing software is software Pix4 DMapper.
3. The intelligent assessment damage assessment method of the intelligent assessment damage assessment system for rice lodging based on deep learning of claim 1, characterized by comprising the following steps:
step one, acquiring an unmanned aerial vehicle image;
step two, the fast splicing software carries out fast splicing on the unmanned aerial vehicle remote sensing sequence images with the overlapping degree to form complete lodging images containing information of all land parcels of the peasant household;
step three, the image data loading module loads the spliced complete lodging image, the polygon drawing module is used for drawing an edge according to the complete lodging image, the edge clearing module clears a line that the drawn edge is not matched with the complete lodging image, the cutting module cuts the lodging image with the edge cleared according to a preset farmer land parcel standard, and the image data storage module stores the cut lodging image;
step four, the disaster recognition module recognizes the image of the right plot area obtained after cutting, and recognizes the rice lodging area in the right plot area;
step five, the disaster situation statistical module matches the screened disaster-suffered images with farmers, compares the disaster-suffered images with the lodging images and counts the disaster-suffered proportion;
and sixthly, the confirmation list output module is used for matching the peasant household information with the disaster-suffered image, and further outputting a disaster-suffered assessment damage assessment report.
4. The method for evaluating and damage-fixing of intelligent rice lodging evaluation and damage-fixing system based on deep learning of claim 3 is characterized in that in step four, the clipped lodging image is transmitted to a disaster identification module, the disaster identification module divides the lodging image into sub-blocks with fixed sizes according to the size of the input image, each sub-block is respectively input into a convolutional neural network model to identify and predict a rice lodging area, a first pixel area in the prediction result is defined to represent the lodging area, and a second pixel area is defined to represent other areas.
5. The method as claimed in claim 3, wherein in step five, the damaged area ratio is counted after removing the black edge left in the image according to the pixel value of the damaged image edge region.
6. The assessment damage assessment method of the intelligent rice lodging assessment damage assessment system based on deep learning of claim 3, wherein in the sixth step, the disaster assessment damage assessment report comprises farmer information, a disaster area and a disaster image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910983753.1A CN110751639A (en) | 2019-10-16 | 2019-10-16 | Intelligent assessment and damage assessment system and method for rice lodging based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910983753.1A CN110751639A (en) | 2019-10-16 | 2019-10-16 | Intelligent assessment and damage assessment system and method for rice lodging based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110751639A true CN110751639A (en) | 2020-02-04 |
Family
ID=69278573
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910983753.1A Pending CN110751639A (en) | 2019-10-16 | 2019-10-16 | Intelligent assessment and damage assessment system and method for rice lodging based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110751639A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111652893A (en) * | 2020-04-22 | 2020-09-11 | 中国科学院城市环境研究所 | Method and equipment for evaluating loss of typhoon to urban tree ecosystem |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1653487A (en) * | 2002-05-10 | 2005-08-10 | 比特波伊斯有限责任公司 | Graphics engine with edge drawing unit and electronic device and memory incorporating a graphics engine |
US20130330001A1 (en) * | 2012-06-06 | 2013-12-12 | Apple Inc. | Image Fusion Using Intensity Mapping Functions |
CN104574339A (en) * | 2015-02-09 | 2015-04-29 | 上海安威士科技股份有限公司 | Multi-scale cylindrical projection panorama image generating method for video monitoring |
CN106327551A (en) * | 2016-08-30 | 2017-01-11 | 华侨大学 | Painting automatic enframing method based on edge detection and image splicing |
CN106504189A (en) * | 2016-11-29 | 2017-03-15 | 福建四创软件有限公司 | A kind of ocean disaster area extracting method based on GIS |
CN108447123A (en) * | 2018-03-27 | 2018-08-24 | 贵州电网有限责任公司输电运行检修分公司 | A kind of power transmission line corridor geological disaster investigation method and system |
CN109214270A (en) * | 2018-07-13 | 2019-01-15 | 中国地质调查局南京地质调查中心 | Doubtful illegal land used information rapid extracting method based on unmanned plane image |
CN109544579A (en) * | 2018-11-01 | 2019-03-29 | 上海理工大学 | A method of damage building is assessed after carrying out calamity using unmanned plane |
CN109813286A (en) * | 2019-01-28 | 2019-05-28 | 中科光启空间信息技术有限公司 | A kind of lodging disaster remote sensing damage identification method based on unmanned plane |
CN109977924A (en) * | 2019-04-15 | 2019-07-05 | 北京麦飞科技有限公司 | For real time image processing and system on the unmanned plane machine of crops |
CN110245644A (en) * | 2019-06-22 | 2019-09-17 | 福州大学 | A kind of unmanned plane image transmission tower lodging knowledge method for distinguishing based on deep learning |
-
2019
- 2019-10-16 CN CN201910983753.1A patent/CN110751639A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1653487A (en) * | 2002-05-10 | 2005-08-10 | 比特波伊斯有限责任公司 | Graphics engine with edge drawing unit and electronic device and memory incorporating a graphics engine |
US20130330001A1 (en) * | 2012-06-06 | 2013-12-12 | Apple Inc. | Image Fusion Using Intensity Mapping Functions |
CN104574339A (en) * | 2015-02-09 | 2015-04-29 | 上海安威士科技股份有限公司 | Multi-scale cylindrical projection panorama image generating method for video monitoring |
CN106327551A (en) * | 2016-08-30 | 2017-01-11 | 华侨大学 | Painting automatic enframing method based on edge detection and image splicing |
CN106504189A (en) * | 2016-11-29 | 2017-03-15 | 福建四创软件有限公司 | A kind of ocean disaster area extracting method based on GIS |
CN108447123A (en) * | 2018-03-27 | 2018-08-24 | 贵州电网有限责任公司输电运行检修分公司 | A kind of power transmission line corridor geological disaster investigation method and system |
CN109214270A (en) * | 2018-07-13 | 2019-01-15 | 中国地质调查局南京地质调查中心 | Doubtful illegal land used information rapid extracting method based on unmanned plane image |
CN109544579A (en) * | 2018-11-01 | 2019-03-29 | 上海理工大学 | A method of damage building is assessed after carrying out calamity using unmanned plane |
CN109813286A (en) * | 2019-01-28 | 2019-05-28 | 中科光启空间信息技术有限公司 | A kind of lodging disaster remote sensing damage identification method based on unmanned plane |
CN109977924A (en) * | 2019-04-15 | 2019-07-05 | 北京麦飞科技有限公司 | For real time image processing and system on the unmanned plane machine of crops |
CN110245644A (en) * | 2019-06-22 | 2019-09-17 | 福州大学 | A kind of unmanned plane image transmission tower lodging knowledge method for distinguishing based on deep learning |
Non-Patent Citations (1)
Title |
---|
祝思君: "基于深度学习的无人机遥感图像目标识别方法研究", 《信息科技辑》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111652893A (en) * | 2020-04-22 | 2020-09-11 | 中国科学院城市环境研究所 | Method and equipment for evaluating loss of typhoon to urban tree ecosystem |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102462572B1 (en) | Systems and methods for training object classifiers by machine learning | |
US11131994B2 (en) | Debugging an autonomous driving machine learning model | |
CN108369635B (en) | Method for aerial image acquisition and analysis | |
US20210081698A1 (en) | Systems and methods for physical object analysis | |
CN109801260B (en) | Livestock number identification method and device, control device and readable storage medium | |
CN110084094B (en) | Unmanned aerial vehicle target identification and classification method based on deep learning | |
CN109387828A (en) | Automatic detection and avoidance system | |
CN111222478A (en) | Construction site safety protection detection method and system | |
CN113962274B (en) | Abnormity identification method and device, electronic equipment and storage medium | |
CN113642474A (en) | Hazardous area personnel monitoring method based on YOLOV5 | |
EP2124194B1 (en) | Method of detecting objects | |
CN109297978B (en) | Binocular imaging-based power line unmanned aerial vehicle inspection and defect intelligent diagnosis system | |
CN111213154A (en) | Lane line detection method, lane line detection equipment, mobile platform and storage medium | |
Passos et al. | Automatic detection of Aedes aegypti breeding grounds based on deep networks with spatio-temporal consistency | |
CN116052082A (en) | Power distribution station room anomaly detection method and device based on deep learning algorithm | |
CN110751639A (en) | Intelligent assessment and damage assessment system and method for rice lodging based on deep learning | |
CN114037671A (en) | Microscopic hyperspectral leukocyte detection method based on improved fast RCNN | |
CN112509321A (en) | Unmanned aerial vehicle-based driving control method and system for urban complex traffic situation and readable storage medium | |
CN116188872A (en) | Automatic forestry plant diseases and insect pests identification method and device | |
CN115546191A (en) | Insulator defect detection method and device based on improved RetinaNet | |
CN114169404A (en) | Method for intelligently acquiring quantitative information of slope diseases based on images | |
CN114549628A (en) | Power pole inclination detection method, device, equipment and storage medium | |
Castellucci et al. | Pole and crossarm identification in distribution power line images | |
CN113989684A (en) | Method and system for marking and grading machine inspection defect picture images | |
CN116883951B (en) | High-speed constructor identification method and device based on multi-source information perception and application thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200204 |
|
RJ01 | Rejection of invention patent application after publication |